-
# Summary
Currently we have two "eval" scripts for measuring performance of LLMs post quantization: https://github.com/pytorch/ao/blob/main/torchao/_models/llama/eval.py,
https://github.com/pytorch/…
-
Hi, there seems a little problem in the code.When im doing the zero-shot experiment, I run
CUDA_VISIBLE_DEVICES=0 python main.py --config cfgs/pointmae_configs/fewshot.yaml --finetune_model --ckpts …
-
## 🚀 Feature Request
Allow passing `num_proc`/`num_workers` parameter in`InContextLearningDataset` so that preparation of dataset can use more than one processes.
## Motivation
When loading bigg…
-
Create a pipeline that integrates Retrieval-Augmented Generation (RAG) based on the LPI dataset, a vector database, and a Large Language Model (LLM).
- [ ] Use the vector database to provide the LLM …
-
I'm using `pai-easynlp 0.0.3` installed by pip.
I copy the training command from [here](https://www.yuque.com/easyx/easynlp/ochmnf) and modify a little.
```
echo '=========[ Fewshot Training: CP-…
-
Hi!
It's a very interesting work and I try to reproduce the results in your paper. However, I run the code in the readme file with the default config, namely images_all_exemplars.py, and I get some…
-
Hi
I am running this command
```
python3 cli.py --method pet --arch_method default --data_dir /data/home/rkarimi/codes/fewshot/internship/fewshot/temp/FewNLU/data/fewg…
-
## 一言でいうと
Few-shotの画像認識で、クラス間の階層構造を利用した研究。クラス間に共通する上位クラスを認識できるようにすることで、分類クラス数が多くなってもメタ認識を活用できるようにする。上位クラスは、クラス名のWord2Vec上の類似度を使用する方法をとっている。
![image](https://user-images.githubusercontent.com/544…
-
Anyone have a backup file in your program?
`python train_meta.py cfg/metayolo.data cfg/darknet_dynamic.cfg cfg/reweighting_net.cfg darknet19_448.conv.23
/home/myh/Documents/program/few-shot-learning…
-
why do you extract 5k imgaes from val set instead of using all the val set images for novel fine-tuning?